© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3705
    Prev
    Next
    INDEX
    Explanations

    significant punctuation marks and formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baugh
    -0.07
     nied
    -0.06
    zÄĻ
    -0.06
    å±
    -0.06
    -http
    -0.06
    hardt
    -0.06
     Sullivan
    -0.06
    .driver
    -0.05
    AMIL
    -0.05
    lycer
    -0.05
    POSITIVE LOGITS
    osl
    0.07
    APS
    0.07
    udeau
    0.07
    aps
    0.07
    iten
    0.06
     Hlav
    0.06
    otp
    0.06
     agreeing
    0.06
    observer
    0.06
    ihn
    0.06
    Activations Density 0.004%

    No Known Activations